Optimization

Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models ACL 2026 Lens Component Deletion based on Differentiable Ray Tracing CVPR 2026 LRDUN: A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive Imaging CVPR 2026 Machine Unlearning via Adaptive Gradient Reweighting and Multi-stage Objective Optimization CVPR 2026 ManifoldNeuS: Manifold-aware View Optimizability for Pose-Free Neural Surface Reconstruction CVPR 2026 Nested Subspace Learning with Flags JMLR 2026 ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling WACV 2026 On the Convergence of Overparameterized Problems: Inherent Properties of the Compositional Structure of Neural Networks L4DC 2026 On the Convergence of Self-Improving Online LLM Alignment UAI 2026 On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials COLT 2026 Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup–Stable–Decay (Extended Abstract) COLT 2026 Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs OSDI 2026 Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection JMLR 2026 Optimizing Packing and Shuffling Strategies for Enhanced Performance in Generative Language Models ACL 2026 Parallelised Differentiable Straightest Geodesics for 3D Meshes CVPR 2026 Progressive Neural Architecture Generation CVPR 2026 RADAR: VQ-VAE Decoder of VAR is a Good Student for Restoring Against Degradation by Acceleration CVPR 2026 Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence CVPR 2026 SCoRe: Salience-Coverage Reduction for Vision Token Pruning in Vision-Language Models CVPR 2026 SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning ACL 2026 SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering WACV 2026 Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Prediction CVPR 2026 SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer CVPR 2026 STDE++: Polynomial-Time Amortization for Linear Differential Operators JMLR 2026 Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting ACL 2026